all AI news
InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation. (arXiv:2309.13516v2 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Indoor monocular depth estimation has attracted increasing research interest.
Most previous works have been focusing on methodology, primarily experimenting
with NYU-Depth-V2 (NYUv2) Dataset, and only concentrated on the overall
performance over the test set. However, little is known regarding robustness
and generalization when it comes to applying monocular depth estimation methods
to real-world scenarios where highly varying and diverse functional
\textit{space types} are present such as library or kitchen. A study for
performance breakdown into space types is essential to …
arxiv cs.cv dataset methodology nyu performance research robustness set space test type